more file format support

crazy_functions/rag_fns/rag_file_support.py

@@ -1,22 +1,16 @@
 import os
 from llama_index.core import SimpleDirectoryReader
 
-# 保留你原有的自定义解析函数
-from PyPDF2 import PdfReader
+supports_format = ['.csv', '.docx', '.epub', '.ipynb',  '.mbox', '.md', '.pdf',  '.txt', '.ppt',
+                   '.pptm', '.pptx']
 
-def extract_text_from_pdf(file_path):
-    reader = PdfReader(file_path)
-    text = ""
-    for page in reader.pages:
-        text += page.extract_text() + "\n"
-    return text
 
 # 修改后的 extract_text 函数，结合 SimpleDirectoryReader 和自定义解析逻辑
 def extract_text(file_path):
     _, ext = os.path.splitext(file_path.lower())
 
     # 使用 SimpleDirectoryReader 处理它支持的文件格式
-    if ext in ['.txt', '.md', '.pdf', '.docx', '.html']:
+    if ext in supports_format:
         try:
             reader = SimpleDirectoryReader(input_files=[file_path])
             documents = reader.load_data()
@@ -25,10 +19,4 @@ def extract_text(file_path):
         except Exception as e:
             pass
 
-    # 如果 SimpleDirectoryReader 失败，或文件格式不支持，使用自定义解析逻辑
-    if ext == '.pdf':
-        try:
-            return extract_text_from_pdf(file_path)
-        except Exception as e:
-            pass
     return None